Video Friday: Robot Dog Shows Off Its Muscles
Video Friday: Robot Dog Shows Off Its Muscles
This week's selection of robotics videos from IEEE Spectrum Robotics is a treasure trove of innovative designs, cutting-edge technologies, and fascinating applications. From a robotic dog that mimics the biomechanical functions of a real dog to a system that transforms speech into physical objects using 3D generative AI, we explore the latest advancements in robotics and their potential to revolutionize various industries.
Mimicking the Muscles of a Real Dog
The Suzumori Endo Lab at Science Tokyo has developed a dog musculoskeletal robot using thin McKibben muscles. This robot mimics the flexible "hammock-like" shoulder structure to investigate the biomechanical functions of dog musculoskeletal systems. The robot's design allows it to move its limbs in a more natural and flexible way, making it an excellent example of biomimicry in robotics.
Transforming Speech into Physical Objects
Researchers at MIT have developed a system that transforms speech into physical objects using 3D generative AI and discrete robotic assembly. By leveraging natural language, the system makes design and manufacturing more accessible to people without expertise in 3D modeling or robotic programming. This technology has the potential to democratize manufacturing and enable people to create complex objects with ease.
Edge AI for Robotics and Automation
Luxonis has developed a fully self-contained vision system built for robotics, automation, and real-world intelligence. The OAK 4 device brings compute, sensing, and 3D perception together in one device, making it an ideal solution for applications that require advanced computer vision capabilities.
Robotic Grippers Inspired by Vines
Engineers at MIT and Stanford University have developed a robotic gripper that can snake around and lift a variety of objects, including a glass vase and a watermelon. The gripper's design is inspired by the twisty tenacity of vines, making it a gentler and more versatile alternative to conventional gripper designs.
Automatic Limb Attachment System
Researchers have developed an automatic limb attachment system using soft actuated straps and a magnet-hook latch for wearable robots. The system enables fast, secure, and comfortable self-donning across various arm sizes, supporting clinical-level loads and precise pressure control.
Autonomous Driving and AI Safety
Waymo is prioritizing demonstrably safe AI, where safety is central to how they engineer their models and AI ecosystem from the ground up. This approach is crucial for autonomous driving, which is the ultimate challenge for AI in the physical world.
AI-Powered Robotic Dog for Disaster Zones
Texas A&M engineering students have built an AI-powered robotic dog that can climb through rubble, avoid hazards, and make autonomous decisions in real-time. The robot uses a custom multimodal large language model (MLLM) combined with visual memory and voice commands to see, remember, and plan its next move like a first responder.
Aerial Microrobots with Speed and Agility
MIT researchers have demonstrated aerial microrobots that can fly with speed and agility comparable to their biological counterparts. A collaborative team designed a new AI-based controller for the robotic bug that enabled it to follow gymnastic flight paths, such as executing continuous body flips.
Sound of a Martian Dust Devil
NASA's Perseverance rover has captured the sound of an electrical discharge as a Martian dust devil flies over the rover. The recording was collected on Oct. 12, 2024, the 1,296th Martian day, or sol, of Perseverance's mission on the Red Planet.
Robots that Think, Plan, and Do
In this episode, we open the archives on host Hannah Fry's visit to Google DeepMind's California robotics lab. Filmed earlier this year, Hannah interacts with a new set of robots—those that don't just see, but think, plan, and do. Watch as the team goes behind the scenes to test the limits of generalization, challenging robots to handle unseen objects autonomously.
Haptic Illusions in VR and AR
Parastoo Abtahi from Princeton University presents her research on "When Robots Disappear – From Haptic Illusions in VR to Object-Oriented Interactions in AR." Advances in audiovisual rendering have led to the commercialization of virtual reality (VR); however, haptic technology has not kept up with these advances. By understanding human perception through the lens of sensorimotor control theory, Abtahi's research explores how to design interactions that not only overcome the current limitations of robotic hardware for VR but also extend our abilities beyond what is possible in the physical world.
Conclusion
This week's selection of robotics videos showcases the latest advancements in robotics and their potential to revolutionize various industries. From biomimicry to AI-powered robots, we explore the cutting-edge technologies and fascinating applications that are changing the world. As we continue to push the boundaries of what is possible with robotics, we must also consider the implications of these advancements on society and the environment. As we look to the future, it is clear that robotics will play an increasingly important role in shaping our world, and it is essential that we continue to invest in research and development to ensure that these technologies are used for the greater good.
